© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5853
    Prev
    Next
    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -1.31
     ModelExpression
    -0.90
     tartalomajánló
    -0.89
    writeFieldEnd
    -0.88
    sidemargin
    -0.84
    migrationBuilder
    -0.83
     />';
    -0.82
    IVEREF
    -0.82
    出版年
    -0.82
    fromnode
    -0.82
    POSITIVE LOGITS
     or
    0.53
     normal
    0.53
     structure
    0.48
     form
    0.48
     constantly
    0.46
     as
    0.45
     regular
    0.44
     ordinary
    0.44
    structure
    0.42
     shape
    0.41
    Activations Density 0.004%

    No Known Activations